Related papers: Audits as Evidence: Experiments, Ensembles, and En…
Statistical fairness metrics in AI-driven credit decisions conflate two causally distinct mechanisms: discrimination operating directly from a protected attribute to a credit outcome, and structural inequality propagating through legitimate…
This paper studies distributed binary test of statistical independence under communication (information bits) constraints. While testing independence is very relevant in various applications, distributed independence test is particularly…
In clinical studies upon which decisions are based there are two types of errors that can be made: a type I error arises when the decision is taken to declare a positive outcome when the truth is in fact negative, and a type II error arises…
The proliferation of personalized recommendation technologies has raised concerns about discrepancies in their recommendation performance across different genders, age groups, and racial or ethnic populations. This varying degree of…
We test whether lying aversion can steer equilibrium selection in mechanism design. In a principal-worker environment, the direct mechanism admits two dominant-strategy equilibria: the designer's target and a worker-optimal outcome. We show…
We propose a method to test for the presence of differential ascertainment in case-control studies, when data are collected by multiple sources. We show that, when differential ascertainment is present, the use of only the observed cases…
Remote pair programming is widely used in software development, but no research has examined how race affects these interactions. We embarked on this study due to the historical under representation of Black developers in the tech industry,…
We develop inference for a two-sided matching model where the characteristics of agents on one side of the market are endogenous due to pre-matching investments. The model can be used to measure the impact of frictions in labour markets…
We analyze 6.7 million case law documents to determine the presence of gender bias within our judicial system. We find that current bias detectino methods in NLP are insufficient to determine gender bias in our case law database and propose…
Perceived discrimination is common and consequential. Yet, little support is available to ease handling of these experiences. Addressing this gap, we report on a need-finding study to guide us in identifying relevant technologies and their…
Large language models (LLMs) are increasingly used in clinical settings, raising concerns about racial bias in both generated medical text and clinical reasoning. Existing studies have identified bias in medical LLMs, but many focus on…
Machine learning models often preserve biases present in training data, leading to unfair treatment of certain minority groups. Despite an array of existing firm-side bias mitigation techniques, they typically incur utility costs and…
While substantial efforts in anti-trafficking research and practice have focused on identifying and assisting victims after exploitation occurs, comparatively less attention has been paid to preventing victimization at the recruitment…
Why do biased predictions arise? What interventions can prevent them? We evaluate 8.2 million algorithmic predictions of math performance from $\approx$400 AI engineers, each of whom developed an algorithm under a randomly assigned…
We are interested in developing a data-driven method to evaluate race-induced biases in law enforcement systems. While the recent works have addressed this question in the context of police-civilian interactions using police stop data, they…
Participation incentives is a well-known issue inhibiting randomized controlled trials (RCTs) in medicine, as well as a potential cause of user dissatisfaction for RCTs in online platforms. We frame this issue as a non-standard…
As generative AI tools are increasingly used to portray people in professional roles, understanding their racial and gender representational biases is critical. We audit over 1.5 million occupational personas generated by four major large…
Digital ads on social-media platforms play an important role in shaping access to economic opportunities. Our work proposes and implements a new third-party auditing method that can evaluate racial bias in the delivery of ads for education…
Prior work on fairness in large language models (LLMs) has primarily focused on access-level behaviors such as refusals and safety filtering. However, equitable access does not ensure equitable interaction quality once a response is…
Conducting disparity assessments at regular time intervals is critical for surfacing potential biases in decision-making and improving outcomes across demographic groups. Because disparity assessments fundamentally depend on the…